Towards automatic personalised content creation for racing games

By Julian Togelius, R. D. Nardi, Simon M. M. Lucas. 2007 IEEE Symposium on Computational Intelligence and Games, 2007

315 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Super mario evolution (2009, methodology): “Recently proposed methods for meeting these demands assume that there is already an RL algorithm in place capable of learning to play the particular game that is being adapted [3], [4], [5] and/or models of player experience [6].”
Experience-Driven Procedural Content Generation (2011, background): “in [40]); in a dynamic evaluation function the agent changes during the game and the quality value somehow incorporates this change (e.”
Imitation Learning (2017, methodology): “Togelius et al. [2007] also used evolutionary algorithms to optimize multiple objectives in a racing game.”
Increasing generality in machine learning through procedural content generation (2019, methodology): “[1, 15, 16] PCGML with constrained sampling [17] Standard search-based [18, 19, 20, 21, 22] Latent Variable Evolution [23, 24] PCGRL [25] Generative Playing Networks [26] Activation Maximization [27] Simple Data Augmentation [8, 9] Uniform Domain Randomization [10] Guided Domain Randomization [28]…”